© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 453
    Prev
    Next
    INDEX
    Explanations

    instances of contradiction or conflict in reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    argumentative or critical phrases about systemic problems and societal issues.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sí
    -0.36
     linkovi
    -0.36
     vig
    -0.35
    帖最后由
    -0.35
    ulink
    -0.35
     Penh
    -0.34
     notably
    -0.33
    あくまで
    -0.32
    нование
    -0.32
     ↓,
    -0.32
    POSITIVE LOGITS
    uxxxx
    0.73
    windowFixed
    0.66
    msgTypes
    0.65
    featureID
    0.65
     resourceCulture
    0.58
     suddenly
    0.58
    suddenly
    0.58
    majánló
    0.58
    Viited
    0.55
    InitVars
    0.54
    Activations Density 0.174%

    No Known Activations